I thought you did not want to guess, at least that’s what you suggested to us in the other topic.
I’m relieved to see this type of transparency from the team. They seem to clearly understand the issue and are ready and willing to communicate such to customers, which seems to be a rarity nowadays…
Despite that, I still feel that the “release” of v3 was rushed. In software, a ground-up rewrite is very much considered a nuclear option, and they must have had some seriously deep issues with v2 for it to have been taken. A ground-up rewrite will of course be riddled with bugs and other problems, but to release a product in such a state is not good. It’s highly unlikely a developer made that decision - much more likely someone in higher management with more of a focus on the bottom line, and possibly less understanding of the technical aspect.
I’m encouraged by the team’s communication and eagerly await the “real” v3. Until then, this rebranded beta test will continue, and as much as it pains me to do so, v3 will not improve unless people focus on using it and reporting bugs and issues to the team. It just sucks that v2 is objectively the better choice for wanting to get things done (with the software we paid for) versus testing a slow and unstable version.
If anyone from Topaz is reading, allow me to make a suggestion - right now, we are paying a time-based license for usage of VEAI. I would rather spend that time using v2, but you need to beta test v3 properly. How about a bug-bounty whereby newly-reported issues are rewarded with say +1 month to license, or some other time bonus? Please, give us a reason to use v3 over v2 and help it along to its full potential that you already envision.
I think the development might take longer than they expected.
The post about the new development of V3.0 was posted in February. They have released 40 versions of alpha, 11 versions of beta and 8 versions of Early Access in last 9 months.
There are only very few active beta testers in this forum, so I understand why they want to release it early. It allow more users to test the program and speedup the debug speed.
So every users who have problem with V3.0 don’t uninstall it immediately, please send your log to developer, this will help them figure out the problem faster.
I have been critical of V3 – but I am starting to have a change of heart. I am seeing a better way to manage projects and more fine tuning options.
The GUI is starting for feel more natural. I haven’t tried stability of the software for clips over a minute — but I’m starting to see the light with this.
I do wish there was better moderation on the forums. It is a headache to scroll through issues on PC Video cards, when I have a Mac. I really feel that more technical issues should be organized. Keep the Beta Testers (as I assume they are privy to more information) in a locked group. It just adds confusion.
But I’m going to stay on board and see how this goes.
My apologies for previous criticisms.
I do feel that this is a different piece of software and it appears to have a different name, slightly? It would be nice to start at V1 with the new name. Because V3 and V2.6.4 are apples and oranges.
Just my thoughts.
Finally — please if there could be reference video files that everyone could use for testing, so that we all have the same source, that would solve so many questions.
I think there just needs to be one spokesperson for announcements. No I heard they would do this or that. Keep one voice.
Beta testers already have a private section within this forum. Are you saying they shouldn’t be allowed to contribute to the general discussions?
I like the possibility to play canceled jobs in the TVEAI, in TVAI the clips are just 0kb. Maybe one instant jpg still would be nice also in TVAI when jumping between presets.
If they are privy to information thst others do not have then it would make sense to keep them separate.
There has been changed so much in therms of A.I. Developement in the last year.
Because people start to understand whats happening and how a neural network does handle its data.
Despite its problems, TVAI 3.X has been the best thing to happen to my workflow since I discovered the product over a year ago.
As it stands, TVAI v3.0.5 does not compare to VEIA v2.6.4. TVAI’s performance and results are a lot worse, upscaling isn’t as sharp, interpolation has more artifacts and makes the output blurry for some reason, and the time it takes to process everything takes significantly longer. Even the compare view is gone, like why?
Where? I looked and can’t find. Thanks
I agree with you, version 2 seemed sharper to me, but i will say this, i did some experimentation in version 3 and i noticed that proteus was blurrier than artemis, which is crazy because in version 2 proteus was sharper. so in version 3 i would suggest using artemis low quality for getting it sharper until they fix proteus to match how it worked in version 2
Here is a sample showing how sharper artermis low quality looks compared to the original dvd quality. Artermis looks good on old dvd quality in 3.0 from what i can tell. hope this helps others. Video AI Team, please fix the proteus model in 3.0 because in 2.0 proteus was the sharpest and clearest model but it doesnt really have that clarity in 3.0. thanks for all your hard work, i know its not easy to work on this for months. We all want it to be the best and that is why we provide the feedback. thanks again
I disagree with that, but saying that without even mentioning what model your using is pointless. GHQ is still fine, Proteus actually looks better and I find myself using AHQ now which I did not in the past. DDV is great when used on interlaced material. I got over trying to upscale garbage quite some time ago so I have no idea how that goes.
When they first released v2.x with chronos I tried it and chronos took forever and went back to using flowframes. Now that Chronos can be ganged in with an upscale, and it’s actually way faster considering, I don’t use flowframes at all anymore, unless of course the video doesn’t need upscaling. I have not tried V3 on my AMD 6900xt since the first release version but it was way too slow on AMD, it’s much better on Nvidia. V2 was fine on AMD
After getting used to V3, I can say it’s pretty good. There are a few interface and workflow tweaks that need to be addressed but I still have V2 installed on the main video box and I never use it anymore.
Proteus in TVAI v3.0.5 is worse than VEIA v2.6.4. It’s not as sharp even with the same settings and takes about 100% longer to render (1h 15m from 1080p 60fps to 4K before, 3h now). Proteus has always been the best upscaling method, many people don’t know how to use it and wrongly claim Artemis or any other model is better for generic upscaling. Comparing the two (custom settings for Proteus and Artemis) in VEAI, Artemis looked like it didn’t do anything before, which it still does in TVAI, comparatively. Chronos Fast has more interpolation artifacts than the earlier version and blurs the output video which it didn’t before and like everything else, takes longer (45m for 1080p 24fps to 60fps before, 1h 30m+ now). I’ve used VEIA consistently for the past year and a half for interpolation and upscaling and I can tell without comparing (I have BTW) that the results and performance of the latest version of TVAI is poor. I’m not planning on switching my workflow until I can get equal or better results. I have an Nvidia GPU. Don’t get me wrong, I love Topaz and their products, but TVAI needs to be overhauled if it wants to compete with its predecessor.
This is only half true.
Artemis models in around version 2 and newer are worse - any Artemis model newer than V8, which was most of them through much of version 2’s release - is worse than Proteus in most circumstances. However, Artemis V8 and earlier, meaning you have to use older versions of Topaz, were significantly better in detail enhancement than Proteus can get right up to latest 3.0.5 release of Topaz.
I also have sunk an insane amount of hours into Proteus since its inception, and I can rarely match the output of the older Artemis, and when it gets close, it gets more artificial as it doesn’t enhance fine detail well. I have been trying, and failing, for months and hundreds of tests now to try and get any of the Proteus versions to outmatch the older models of Artemis without success.
The sad state of it is that due to Artemis being broken around version 2, Proteus is the best upscaling option current in the program, so the statement is correct for most people - its just that its become that way because the older Artemis models don’t work anymore and the quality reduction seems to have been accepted to prioritise user manual sliders for adjustments.
I suspect this is largely a side effect of Topaz trying to move away from models that need a lot of adjustments prior to importing the media (what you fed in makes a large change to the output) to a model solution that tries to make it a “one stop shop” for a general user.
I don’t disagree with that end goal, but it did sacrifice quality in the models to achieve it presently. I am just patiently waiting for improvements to the Proteus models to catch up to where Artemis was originally. At that point, then it will be the best model for upscaling.
I was using the 2.x version almost all day and for up to 18 hours nonstop for one file after another. Since version 3.x my work stopped. After months hoping vor a 3.x version that at least matches the usability, speed and output quality of version 2.x I feel totally screwed up not being able to continue my work either with the old version because any further support is abandoned nor with the new version that lacks fundamental. Or to say in different words: we are still waiting for the manufacturer to find the perfect color tone of pink with a note of magenta in between instead of getting the damn porsche to run, which it should normally be made for …
It would be interesting to hear about sales.
Because V3 looks like some GUI for some command line tool made by geeks for geeks. It looks like some student project and works like some student project. And it is not good for sales… To sale something you need product with first look impression, style and some magic inside. V2 had magic and style and V3 absolutely not.
Seriously? Bilinear frame resizing in previews? And how can we call it “previews”? If you can’t make normally working preview, just remove it until it will be completely fixed. When you see glitches in first minute of testing, you never make a decision to buy something. This is the basics.
So, it would be sad to lose such promising Topaz team with unique products because of financial fail…